Face Transfer with Generative Adversarial Network
Runze Xu, Zhiming Zhou, Weinan Zhang, Yong Yu
TL;DR
This paper introduces an end-to-end face transfer method using GANs, specifically CycleGAN and PatchGAN, to animate target characters with source actor performances, improving video quality.
Contribution
It presents a novel GAN-based approach for face transfer that integrates CycleGAN and PatchGAN, enhancing realism without traditional face modeling.
Findings
Effective face transfer with realistic results
Improved video quality through PatchGAN
Exploration of receptive field effects on image quality
Abstract
Face transfer animates the facial performances of the character in the target video by a source actor. Traditional methods are typically based on face modeling. We propose an end-to-end face transfer method based on Generative Adversarial Network. Specifically, we leverage CycleGAN to generate the face image of the target character with the corresponding head pose and facial expression of the source. In order to improve the quality of generated videos, we adopt PatchGAN and explore the effect of different receptive field sizes on generated images.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFace recognition and analysis · Generative Adversarial Networks and Image Synthesis · Advanced Image Processing Techniques
MethodsBatch Normalization · Residual Connection · *Communicated@Fast*How Do I Communicate to Expedia? · Tanh Activation · Residual Block · Instance Normalization · Convolution · HuMan(Expedia)||How do I get a human at Expedia? · Sigmoid Activation · GAN Least Squares Loss